eachlabs-voice-audio — Claude Code skill: TTS and transcription
A skill that wires EachLabs voice and audio models into your agent: speech synthesis, transcription, speaker separation and voice conversion.
npx skills add eachlabs/skills --skill eachlabs-voice-audio -a claude-codeWhat eachlabs-voice-audio does
The skill documents the EachLabs Predictions API flow. Your agent validates a model by slug with GET https://api.eachlabs.ai/v1/model?slug=<slug> to read the exact request_schema, submits a job to POST https://api.eachlabs.ai/v1/prediction at version "0.0.1", then polls GET https://api.eachlabs.ai/v1/prediction/{id} until the status reads "success" or "failed".
Model tables cover three areas. Speech synthesis includes ElevenLabs TTS, a variant that returns word timings, multi-speaker dialogue, sound effects, Kling V1 TTS, Kokoro 82M and Stable Audio 2.5. Transcription lists ElevenLabs Scribe v2, Wizper with timestamps, Whisper, and Whisper Diarization for telling speakers apart. Voice work spans RVC v2, training a custom model with train-rvc, ElevenLabs Voice Clone and Voice Changer, XTTS v2, Open Voice, Chatterbox S2S and video dubbing. Two utilities round it out: merging audio into video with FFmpeg and format conversion.
You need an EachLabs key in the EACHLABS_API_KEY environment variable; it travels in the X-API-Key header. RVC voice conversion pulls a model from custom_rvc_model_download_url, and the skill itself warns to accept only trusted references supplied by the user rather than fetching from arbitrary addresses. No key means no calls go through, so set it before the first run.
What it helps with
- narrate a product video with a chosen voice
- transcribe a call recording and label who spoke
- shift a vocal take into a different timbre
- train a voice model on your own samples
- lay a narration track over existing footage
Example prompts for the agent
- Turn
intro.txtinto speech withelevenlabs-text-to-speechand save the mp3 - Transcribe
meeting.mp3withwhisper-diarization, there are three speakers - Run voice conversion on
vocals.wavwithrvc-v2using my custom model
How to install eachlabs-voice-audio
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-voice-audio -a claude-code2Manually: put the files in place
~/.claude/skills/eachlabs-voice-audio/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/eachlabs-voice-audio/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-voice-audio -a codex2Manually: put the files in place
.agents/skills/eachlabs-voice-audio/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-voice-audio -a cursor2Manually: put the files in place
.cursor/skills/eachlabs-voice-audio/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills eachlabs-voice-audio2Manually: put the files in place
.github/skills/eachlabs-voice-audio/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-voice-audio -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/eachlabs-voice-audioManually: put the files in place
.devin/skills/eachlabs-voice-audio/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill eachlabs-voice-audio -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about eachlabs-voice-audio
How do I install eachlabs-voice-audio in Claude Code?
Run npx skills add eachlabs/skills --skill eachlabs-voice-audio -a claude-code. The skill file lands at ~/.claude/skills/eachlabs-voice-audio/SKILL.md.
What does eachlabs-voice-audio do?
It gives your agent EachLabs models for speech synthesis, audio transcription, speaker diarization, voice cloning and voice conversion, plus utilities such as merging audio with video.
What do I need before using it?
An EachLabs key stored in EACHLABS_API_KEY, sent as the X-API-Key header. Voice conversion with your own model also needs a reference passed in custom_rvc_model_download_url, and the skill asks you to stick to trusted sources.
